© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 12244
    Prev
    Next
    INDEX
    Explanations

    closing braces and related punctuation in code or data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    closing braces and brackets in code.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sus
    -0.34
    zzleHttp
    -0.34
    JspWriter
    -0.33
    tabak
    -0.33
     ujednoznacz
    -0.32
    ORN
    -0.31
     graden
    -0.31
    CLUSIVE
    -0.31
    sw
    -0.30
    atre
    -0.30
    POSITIVE LOGITS
    endregion
    0.60
    InSection
    0.59
    endpush
    0.56
    
    0.55
    Hochspringen
    0.55
    EndInit
    0.55
     esternos
    0.54
    webElementXpaths
    0.54
     kasarigan
    0.53
    DispatchToProps
    0.52
    Activations Density 1.038%

    No Known Activations